OpenVINO toolkit

Developer's DescriptionBy Intel SoftwareDevelop applications and solutions that emulate human vision.Develop multiplatform computer vision solutions with the OpenVINO toolkit. Developers can build and train AI models in the cloud--on popular frameworks such as TensorFlow, MXNet, and Caffe--and deploy them across a broad range of products. Based on convolutional neural networks (CNN), the toolkit includes a library of functions and preoptimized kernels to enable CNN-based deep learning inference at the edge, and optimized calls for OpenCV and OpenVX. It also supports heterogeneous execution across computer vision accelerators--CPU, GPU, Intel Movidius Neural Compute Stick, and FPGA--using a common API.